How to be a Better Colorectal Surgeon? A Sentimental Analysis of Patient Perceptions.

How to be a Better Colorectal Surgeon? A Sentimental Analysis of Patient Perceptions. | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article How to be a Better Colorectal Surgeon? A Sentimental Analysis of Patient Perceptions. Christina Schott, Arthur Drouaud, Brandon Boyarsky, Rachel Silverman, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7133158/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract PURPOSE Due to the sensitive nature of colorectal surgery discussions and exams, patient opinions and attitudes towards their providers are an essential part of quality colorectaal surgery care. There are a multitude of factors related to both providers and patients that impact patients’ opinions. These include factors such as patient and provider demographics, personality traits, communication skills, and disease specific factors. METHODS This study analyzed online reviews to better grasp the relationship between patient sentiment scores and demographics of colon and rectal surgeons (CRS). Analysis of patient reviews was performed using machine learning. Additionally, it looks at how key terms found in patient reviews of CRS relate to overall patient sentiment. RESULTS Analysis included 6,986 patient reviews of 1,378 CRS. Younger surgeon age was associated with higher mean sentiment analysis scores and star ratings (P < .01). After word frequency analysis, our study found that patient reviews containing certain clinically relevant terms had an increased likelihood of receiving a positive review. Additionally, poor communication skills, negative personality traits, and rushed encounters were associated with lower surgeon ratings. CONCLUSION Physician attributes and disease specific factors both significantly impact patients’ opinions. Favorable interpersonal skills of CRS are essential to patient satisfaction. Additionally, our study found that disease specific terms like “pain” and “cancer” were associated with negative reviews indicating that patient satisfaction extends beyond traits inherent to CRS such as demographics and behavior. Colon and rectal surgeons healthgrades Patient satisfaction Physician rating Web sites INTRODUCTION Physician rating websites have a great impact on how patients’ choose their doctors. We are able to gain a better understanding of patients’ desires and concerns about their care by analyzing the reviews of former patients. Therefore, physicians and patients alike can gain meaningful insight on physician rating websites like healthgrades.com about the care that is provided by certain physicians and the attributes of physicians that patients are looking for [ 1 , 2 ]. Through the utilization of artificial intelligence and machine learning, we are able to perform sentiment analysis on large qualitative datasets and analyze text like patient reviews for positive and negative language. Machine learning sentiment analysis allows for a bulk review of patient feedback on physician attitudes, practice cleanliness and efficiency, and medical services provided [ 4 , 5 ]. Previously, sentiment analysis has been conducted on patients of several medical specialties, including psychiatrists, otolaryngologists, and vascular and orthopedic surgeons [ 2 , 6 – 10 ]. These studies found that positive physician reviews include words like “kind,” “confident,” “recommend,” and “comfortable” that describe physician attributes, whereas negative physician reviews included both treatment and physician-specific words like “pain,” “side effects,” and “rude” [ 2 , 6 – 10 ]. This sentiment analysis is the first to be conducted on qualitative reviews of CRS, who must balance treating an expanding patient population with a large number of complex and sensitive disease processes. A previous study conducted by Hill et al assessed quantitative metrics of CRS with numerical ratings [ 11 ]. Disease-specific sentiment analyses pertinent to gastroenterology and colorectal surgery sought to understand patient perspectives on colorectal cancer and Lynch syndrome, respectively [ 12 , 13 ]. We seek to conduct a sentiment analysis of the online reviews on healthgrades.com of CRS. The star ratings on healthgrades.com are based on patient reviews and reflect various aspects of a healthcare provider's service. Patients rate physicians on a scale of 1 to 5 stars, with 1 star indicating poor performance and 5 stars indicating excellent performance. Given that higher patient satisfaction is associated with better surgical outcomes, such as complications, mortality and readmission rates, it is essential to understand patients’ opinions on physician behavior and the care they receive [ 26 ]. However, complications in colorectal surgery, particularly those requiring additional surgeries, have been shown to have a significant negative impact on patient perception of the surgeon and the care they received [ 27 ]. Therefore, this analysis is particularly useful for CRS. MATERIALS & METHODS Colon and Rectal Surgeon data extraction Physicians were identified using the directory from American Society of Colon and Rectal Surgeons (ASCRS). Since healthgrades.com only includes reviews of physicians from the United States, we limited our inclusion criteria to only surgeons practicing in the US. We excluded surgeons without written reviews on healthgrades.com . The surgeon names were inputted into a web-scraping code that searched Google for “(Physician Name) General Surgeon healthgrades.” To ensure we included all colorectal surgeons in our search, we chose to look up general surgeons instead of colorectal surgeons because ASCRS listed rural surgeons under general surgery on healthgrades.com. This resulted in a compilation of healthgrades surgeon profiles included in this study, which were used to pull written and star-rating reviews and demographic information. States included in each region for locational analysis followed the United States Census Bureau regions. Healthgrades was selected as it was consistently in the first five websites offered when searching Google for a provider and one of the only websites that permitted bulk data extraction. Sentiment analysis calculation Sentiment analysis was conducted using “Valence Aware Dictionary and Sentiment Reasoner” (VADER) Python package. VADER is a widely used tool for analyzing and classifying the sentiment of text as positive, negative, or neutral. This classification is made by referencing a dictionary developed by 20 trained human raters, who assigned scores ranging from − 4 (most negative) to + 4 (most positive) to hundreds of words, with 0 representing neutral sentiment. VADER obtained gold standard (human-validated) ground truth regarding sentiment intensity on corpora. For this purpose, 20 independent human raters from AMT were recruited. Quality control processes were implemented to help ensure meaningful data from the AMT raters. First, every rater was prescreened for English language reading comprehension. Second, every prescreened rater then had to complete an online sentiment rating training and orientation session, and score 90% or higher for matching the known (pre-validated) mean sentiment rating of lexical items. The training helped to ensure consistency in the rating rubric used by each independent rater. Third, every batch of 25 features contained five “golden items” with a known (pre-validated) sentiment rating distribution. If a worker was more than one standard deviation away from the mean of this known distribution on three or more of the five golden items, we discarded all 25 ratings in the batch from this worker. Finally, we implemented a bonus program to incentivize and reward the highest quality work. For example, we asked workers to select the valence score that they thought “most other people” would choose for the given lexical feature. This package parses sentences to sum and normalize the associated scores between − 1 (most negative) and + 1 (most positive). It recognizes punctuation, redundant capitalization, and adverbs, adjusting scores based on context. For example, “He was an AMAZING doctor” scores higher than “He was an amazing doctor,” and phrases like “very good” receive higher scores than “good,” while negations such as “not great” are scored negatively. Thus, VADER can provide a nuanced sentiment score for text based on the context and intensity of the words used. Model Validation and Data Analysis Linear regression analysis in Python was used to relate each surgeon’s average sentiment score to their average reported online star score, demonstrating the validity of the sentiment analysis. A significant correlation would indicate that the sentiment scores align with patient-reported star ratings. Student t-tests were performed to evaluate the relationship between sex and average sentiment score, while one-way ANOVA tests were used for age and geographic locations. A word frequency analysis identified the most commonly used words in both the most positive and most negative reviews, excluding non-clinically relevant terms like “fabulous” or “best” to focus on practical insights. A bigram analysis provided context for frequently used words. Sentiment scores > + 0.50 were defined as positive reviews, and scores + 0.50. RESULTS Model Validation When graphing the average score of each review with the calculated sentiment score, we observed a positive linear relationship (r² = 0.439, p < 0.01), which supports the validity of our analysis. Colorectal Surgeon Demographics Of the 4,065 surgeons initially identified, 3,292 U.S based surgeons were included in the final analysis. Healthgrades profiles were for 3,057 surgeons (2,139 males, 918 females). Of those, 1,819 had online reviews and 1,378 had written comments. The age distribution of surgeons was: under 40 (69), 40–49 (443), 50–59 (435), and over 60 (419). Increasing age was associated with decreasing mean sentiment score + 0.567 ± 0.299 for surgeons under 40, + 0.538 ± 0.343 for ages 40–49, + 0.498 ± 0.341 for ages 50–59, and + 0.471 ± 0.365 for those over 60 (p < 0.05) and mean star rating 4.466 ± 0.640 for surgeons under 40, 4.313 ± 0.612 for ages 40–49, 4.206 ± 0.610 for ages 50–59, and 4.102 ± 0.638 for those over 60 (p < 0.05) (Table 1 ). After analyzing a relationship between mean sentiment score and sex and mean star rating and sex, we found that men and women did not have a significant difference in either metric (Table 2 ). Table 1 Sentiment Scores and Mean Star Scores of Colon and Rectal Surgeons based on Age. Age 60 P-value Frequency (N) 69 443 435 419 - Mean Sentiment Score Analysis + 0.567 ± 0.299 + 0.538 ± 0.343 + 0.498 ± 0.341 + 0.471 ± 0.365 0.0149 Mean Star Score Analysis 4.466 ± 0.640 4.313 ± 0.612 4.206 ± 0.610 4.102 ± 0.638 < 0.05* *Statistically significant Table 2 Sentiment Scores and Mean Star Scores of Colon and Rectal Surgeons based on Sex. Sex Male Female p-value Frequency 1034 344 - Mean Sentiment Score Analysis + 0.507 ± 0.343 + 0.506 ± 0.360 0.95 Mean Star Score Analysis 4.256 ± 0.778 4.198 ± 0.878 0.06 Word/Word Pair Reviews A subset of the 6986 reviews analyzed were categorized into positive or negative reviews based on the sentiment scores. Words such as "care," "caring," "kind," "wonderful," and "compassionate" were more commonly used in positive reviews with frequencies of 718, 434, 350, 288, and 240, respectively. However, words such as "no," "pain," "cancer," "care," and "problem" were more commonly used in negative reviews with frequencies of 463, 403, 230, 188, and 159, respectively. The most frequent word pairs in positive reviews were "(kind, caring)" (102), "(saved, life)" (93), "(feel, comfortable)" (90), "(kind, compassionate)" (66), and "(truly, cares)" (62). Conversely, the most common word pairs in negative reviews were "(colon, cancer)" (55), "(no, pain)" (54), "(cancer, free)" (34), "(saved, life)" (34), and "(no, one)" (33). Table 3 Common Words and their Frequencies in Positive and Negative Reviews Positive Reviews Words Frequency (N) Negative Reviews Word Frequency (N) care 718 no 463 caring 434 pain 403 kind 350 cancer 230 wonderful 288 care 188 compassionate 240 problem 159 comfortable 198 rude 137 friendly 185 horrible 83 truly 184 help 79 grateful 174 worst 77 better 166 want 72 Table 4 Common Word-Pairs and Their Frequencies in Positive and Negative Reviews Positive Reviews Word-Pair Frequency (N) Negative Reviews Word-Pairs Frequency (N) (kind, caring) 102 (colon, cancer) 55 (saved, life) 93 (no, pain) 54 (feel, comfortable) 90 (cancer, free) 34 (kind, compassionate) 66 (saved, life) 34 (truly, cares) 62 (no, one) 33 (god, bless) 58 (severe, pain) 28 (caring, compassionate) 56 (excruciating, pain) 26 (make, sure) 55 (waste, time) 23 (took, care) 52 (no, problems) 22 (cares, patients) 51 (emergency, surgery) 21 Multivariate Analysis Multivariate analysis identified words that significantly impact the likelihood that a physician receives a positive or negative review. For example, the word “approachable” increased the likelihood of a physician receiving a positive review (odds ratio (OR): 2.23, p < 0.05), however, the word “rude” decreased the odds of receiving a positive review (OR: 0.09; p < 0.05). Table 5 Multivariant analysis of relevant keywords with a positive influence on reviews. Positive Words OR (97.5% CI) P-value confident 6.49 (3.84–10.96) < 0.05* accessible 6.29 (1.39–28.50) < 0.05* kind 3.80 (2.84–5.08) < 0.05* relief 3.58 (1.32–9.75) < 0.05* pain-free 3.51 (1.27–9.72) < 0.05* recommend 3.05 (2.67–3.48) < 0.05* empathetic 3.01 (0.93–9.66) 0.06 warm 2.80 (1.44–5.42) < 0.05* listens 2.79 (1.91–4.06) < 0.05* comfortable 2.51 (1.96–3.22) < 0.05* explains 2.47 (1.80–3.38) < 0.05* staff 2.31 (1.99–2.68) < 0.05* approachable 2.23 (0.54–9.19) 0.27 bedside-manner 1.97 (1.46–2.66) < 0.05* parking 1.94 (0.31–12.27) 0.48 knowledgeable 1.46 (1.12–1.90) < 0.05* courtesy 1.41 (0.17–11.78) 0.75 advocate 1.39 (0.35–5.49) 0.64 refer 1.37 (0.74–2.52) 0.32 nurse 1.18 (0.84–1.66) 0.34 medication 1.07 (0.47–2.45) 0.88 *Statistically significant Table 6 Multivariant analysis of relevant keywords with negative influence on reviews. Negative Words OR (97.5% CI) P-Value rude 0.094 (0.041–0.215) < 0.05* arrogant 0.117 (0.035–0.395) < 0.05* old 0.520 (0.424–0.637) < 0.05* rushed 0.689 (0.429–1.108) 0.12 severe-pain 0.766 (0.191–3.063) 0.71 walking 0.780 (0.348–1.747) 0.55 emergency 0.837 (0.599–1.170) 0.30 young 0.838 (0.393–1.787) 0.65 organized 0.887 (0.368–2.138) 0.79 *Statistically significant DISCUSSION Increased patient education and ease of access to medical information on the internet are likely contributing to the rapid growth in patient volume experienced by CRS. Reports have shown that 72% of surgeons have a practice website and 43% of patients have searched for their doctors online [ 15 ]. Additionally, the proportion of cases treated by high-volume CRS has also increased, pointing to a potential link between patient education and surgeon selection [ 16 ]. Understanding how physicians are rated and reviewed online is essential to providing the highest quality of care and attracting future patients. The goal of this study is to analyze the language used to describe CRS with high and low patient ratings and identify characteristics associated with those ratings. Our research, which included 1,378 surgeons, is the second-largest cohort to date studied using physician review websites. Additionally, it includes the highest number of written reviews and is the only study to utilize written sentiment for this purpose. We discovered physicians described as caring, kind, compassionate, and comfortable and provide sufficient pain management received the highest ratings on online reviews. Our research shows that there are several key factors that influence patient ratings of CRS. According to a healthgrades.com report on the predictors of high ratings in CRS, younger surgeons with 1–9 years of experience were 2.76 times more likely to receive high ratings, indicating that patients have a more positive perception of younger surgeon [ 11 ]. Similarly, our analysis showed that younger CRS have significantly more positive written reviews ( 59: +0.471; P = .014) and star ratings ( 59: 4.102; P < 0.01) than older surgeons. In light of these findings, we recommend that middle-aged surgeons incorporate these positive characteristics which are described later in this study. These findings are consistent with previous observations that younger surgeons prefer minimally invasive surgical techniques [ 17 ]. Additionally, residencies today emphasize interpersonal skills and communication throughout their selection process which may contribute to more positive patient ratings. Another study analyzed reviews of general surgeons from RateMDs.com and Yelp.com, and found there was no significant gender difference in overall ratings (83.7% positive for men vs. 74.3% for women, P = 0.08) [ 19 ]. Our findings align with this study as we found men had a sentiment score of + 0.507 and women + 0.506 (P = 0.955), with star ratings of 4.256 for men and 4.198 for women (P = 0.0648). Our study found that physician characteristics and interpersonal relationships were more likely to be associated with positive reviews, while words about the patient’s disease were more likely to be associated with negative reviews. These findings are in line with sentiment analysis of patient reviews in other surgical fields [ 2 , 6 – 9 ]. We explored the specific language and drivers behind these findings. Interpersonal characteristics such as active listening and empathetic responses, along with clinical knowledge, have been shown to enhance physician-patient relationships [ 20 ]. Our study found that surgeons were significantly more likely to get positive reviews when they appeared confident (OR: 6.49), accessible (OR: 6.29), listened attentively (OR: 2.79), and were kind (OR: 3.80). Additionally, words such as "care" and "kind" were more frequently used in positive reviews. The four most common words and word pairs in these reviews were associated with interpersonal characteristics. Shared decision making is made possible by quality communication between the patient and provider [ 21 ]. Patients perceive openness, agreeableness, and emotional stability as favorable traits in CRS. Despite acknowledging that a surgeon’s personality may not affect post-operative complication rates, patients believe it would significantly change complication management. This underscores the importance of promoting positive interpersonal characteristics for both patient satisfaction and effective complication management [ 22 ]. Therefore it is essential to continue promoting positive interpersonal characteristics through education, such as patient simulations and constructive feedback. On the other hand, physicians who were perceived as rude (OR: 0.09), arrogant (OR: 0.12), and old (OR: 0.52) were significantly more likely to receive negative reviews. This is consistent with our finding that older surgeons received worse reviews. Moreover, disease and pain-related words were more frequently used in negative reviews. In the field of colon and rectal surgery, 39% of rectal cancer patients reported unclear communication with their physicians, particularly among younger patients and those in larger hospitals, which led to consistently lower scores in role, emotional, and social functioning [ 23 ]. The words “cancer” and “colon-cancer” were among the most frequently used words in negative reviews. Patient disease is a factor outside of physicians control that may negatively impact patient perception and most physicians report having difficulty during these conversations. For example, in the United States, colorectal cancer ranks as the second leading cause of cancer-related deaths; this fact negatively influences patients’ perceptions of providers when they receive a colorectal cancer diagnosis [ 24 ]. Poor doctor-patient communication skills can be linked with adverse outcomes for patients such as higher rates of anxiety and depression, and worse psychological adaptation to their new diagnosis [ 25 ]. Therefore, there is need for improvement in this area of the colorectal cancer community. When delivering ‘bad’ news, physicians should speak in an unhurried, honest, balanced, and empathic fashion to produce greater satisfaction with the encounter. Important aspects of these conversations entail understanding the patient's expectations, giving a forewarning of bad news, discussing this new diagnosis at the patient's preferred pace, giving adequate time for the patient to react, and addressing their questions and concerns. Strategies for improving physician-patient communication include communication training courses for medical students and physicians along with supplying summaries of difficult discussions to improve recollection and satisfaction with communication for patients [ 25 ]. Our findings stress the importance of improved communication techniques for both current and future CRS. Limitations We acknowledge several limitations in this study. Firstly, healthgrades.com was our only source of patient reviews because it was the only place from which we could freely extract data, potentially introducing bias. The reviews on healthgrades.com are not subject to a verification process which allows anyone to write a review about any healthcare provider, potentially impacting the reliability of the information. Additionally, the subjective nature of ratings and reviews on public websites prevented us from understanding the specific reasons behind patients' comments. We couldn't differentiate between remarks about the physician and non-physician factors in our overall sentiment analysis scores. Some other factors that were not readily available to us through healthgrades.com and may be beneficial to review in the future include demographic factors of physicians and their practices such as race, type of practice (academic vs. community), setting of practice; and patient demographics such as race, sexual orientation, and socioeconomic status. Furthermore, by using the "American Society of Colon and Rectal Surgeons" directory to compile our surgeon list, our analysis was limited to a portion of all CRS. Further developments for this study include the creation of an app or website that would give providers a place to input their websites and reviews to receive individualized performance feedback. A machine learning-based app would enable surgeons to receive feedback in real time and adjust their practices as needed. CONCLUSION Our study utilized machine-learning sentiment analysis of online patient reviews to determine positive and negative attributes of CRS. By implementing VADER analysis on healthgrades.com patient reviews, we revealed that younger CRS were more likely to have positive patient reviews and more positive interpersonal characteristics such as empathy and confidence. Poor communication skills, negative personality traits, and rushed encounters were associated with lower patient ratings of CRS. Disease-specific words like “cancer” and “pain” significantly contributed to negative patient opinions. To increase patient satisfaction, we recommend all CRS apply favorable interpersonal skills which are emphasized in more recent medical training. Declarations Funding/Support : No Source of Fundings. Financial Disclosures : No Financial Disclosures Competing Interests: All authors have no competing interests to declare Author Contribution C.S., A.D., B.B., R.S., and M.P. wrote the main manuscript. A.D. prepared all figures and tables. All authors reviewed the manuscript. Data Availability The data collected are available through healthgrades.com using physician names found through https://imis.fascrs.org/portal/portal/Member_Directory/Find-a-Colorectal-Surgeon.aspx?_gl=1*1st49zz*_ga*MTIxNTE0OTc4Ni4xNzUyNzc0MDAx*_ga_M0BRWHHY9M*czE3NTI3NzQwMDEkbzEkZzAkdDE3NTI3NzQwMDEkajYwJGwwJGgw References Leibovich BC (2018) Correlation of Online Physician Reviews and Overall Patient Satisfaction. Mayo Clin Proc . ;93(4):404–405. 10.1016/j.mayocp.2018.02.021 Park SH, Cheng CP, Buehler NJ, Sanford T, Torrey W (2023) A sentiment analysis on online psychiatrist reviews to identify clinical attributes of psychiatrists that shape the therapeutic alliance. Front Psychiatry 14:1174154. 10.3389/fpsyt.2023.1174154 Iglesias CA, Moreno A (eds) (2020) Sentiment Analysis for Social Media. MDPI - Multidisciplinary Digital Publishing Institute. 10.3390/books978-3-03928-573-0 Greaves F, Ramirez-Cano D, Millett C, Darzi A, Donaldson L (2013) Use of sentiment analysis for capturing patient experience from free-text comments posted online. J Med Internet Res 15(11):e239. 10.2196/jmir.2721 Pandey AR, Seify M, Okonta U, Hosseinian-Far A (2023) Advanced Sentiment Analysis for Managing and Improving Patient Experience: Application for General Practitioner (GP) Classification in Northamptonshire. Int J Environ Res Public Health 20(12):6119. 10.3390/ijerph20126119 Vasan V, Cheng CP, Lerner DK, Vujovic D, van Gerwen M, Iloreta AM (2023) A natural language processing approach to uncover patterns among online ratings of otolaryngologists. J Laryngol Otol 137(12):1384–1388. 10.1017/S0022215123000476 Tang J, Arvind V, White CA, Dominy C, Cho S, Kim JS (2023) How are Patients Describing You Online? A Natural Language Processing Driven Sentiment Analysis of Online Reviews on CSRS Surgeons. Clin Spine Surg 36(2):E107–E113. 10.1097/BSD.0000000000001372 Cho LD, Tang JE, Pitaro N et al (2023) Sentiment Analysis of Online Patient-Written Reviews of Vascular Surgeons. Ann Vasc Surg 88:249–255. 10.1016/j.avsg.2022.07.016 Tang JE, Arvind V, White CA et al (2023) Using Sentiment Analysis to Understand What Patients Are Saying About Hand Surgeons Online. Hand (N Y) 18(5):854–860. 10.1177/15589447211060439 Casciato DJ, Mateen S AI-Assisted Sentiment Analysis of ACFAS Fellowship-Trained Foot and Ankle Surgeon Online Reviews. J Foot Ankle Surg . Published online June 13, 2024:S1067-2516(24)00113-3. 10.1053/j.jfas.2024.05.014 Hill SS, Hoang CM, Cheraghi SN et al (2020) Data Accuracy and Predictors of High Ratings of Colon and Rectal Surgeons on an Online Physician Rating Website. Dis Colon Rectum 63(2):226–232. 10.1097/DCR.0000000000001539 Portier K, Greer GE, Rokach L et al (2013) Understanding topics and sentiment in an online cancer survivor community. J Natl Cancer Inst Monogr 2013(47):195–198. 10.1093/jncimonographs/lgt025 Bian J, Zhao Y, Salloum RG et al (2017) Using Social Media Data to Understand the Impact of Promotional Information on Laypeople’s Discussions: A Case Study of Lynch Syndrome. J Med Internet Res 19(12):e414. 10.2196/jmir.9266 Hutto C, Gilbert E (2014) VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text. Proceedings of the International AAAI Conference on Web and Social Media . ;8(1):216–225. 10.1609/icwsm.v8i1.14550 Long LE, Leung C, Hong JS, Wright C, Young CJ (2019) Patterns of internet and social media use in colorectal surgery. BMC Surg 19(1):52. 10.1186/s12893-019-0518-4 Jolly K, Parry J, Rouse A, Stevens A (2001) Volumes of cancer surgery for breast, colorectal and ovarian cancer 1992-97: Is there evidence of increasing sub-specialization by surgeons? Br J Cancer 84(10):1308–1313. 10.1054/bjoc.2001.1794 Dulskas A, Caushaj PF, Grigoravicius D et al (2023) International Society of University Colon and Rectal Surgeons survey of surgeons’ preference on rectal cancer treatment. Ann Coloproctol 39(4):307–314. 10.3393/ac.2022.00255.0036 Lam CC, Zimmern A (2021) Colon and Rectal Surgery Residency Selection Criteria: A National Program Director Survey. J Surg Educ 78(2):519–524. 10.1016/j.jsurg.2020.07.030 Marrero K, King E, Fingeret AL (2020) Impact of Surgeon Gender on Online Physician Reviews. J Surg Res 245:510–515. 10.1016/j.jss.2019.07.047 Tallman K, Janisse T, Frankel RM, Sung SH, Krupat E, Hsu JT (2007) Communication Practices of Physicians With High Patient-Satisfaction Ratings. Perm J . ;11(1):19–29. Accessed August 14, 2024. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3061374/ Austin CA, Mohottige D, Sudore RL, Smith AK, Hanson LC (2015) Tools to Promote Shared Decision Making in Serious Illness: A Systematic Review. JAMA Intern Med 175(7):1213–1221. 10.1001/jamainternmed.2015.1679 Bisset CN, Dames N, Oliphant R et al (2020) Exploring shared surgical decision-making from the patient’s perspective: is the personality of the surgeon important? Colorectal Dis 22(12):2214–2221. 10.1111/codi.15237 Kerr J, Jutta Engel MD, Anne Schlesinger Raab MPH, Hansjorg Sauer MD, Holzel D (2003) PhD. Doctor-Patient Communication. Dis Colon Rectum 46(8):1038–1046. 10.1007/s10350-004-7278-6 Siegel RL, Wagle NS, Cercek A, Smith RA, Jemal A (2023) Colorectal cancer statistics, 2023. Cancer J Clin 73(3):233–254. 10.3322/caac.21772 Ellis PM, Tattersall MH (1999) How should doctors communicate the diagnosis of cancer to patients? Ann Med 31(5):336–341. 10.3109/07853899908995900 Lobo Prabhu K, Cleghorn MC, Elnahas A, Tse A, Maeda A, Quereshy FA, Okrainec A, Jackson TD (2018) Is quality important to our patients? The relationship between surgical outcomes and patient satisfaction. BMJ Qual Saf. ;27(1):48–52. 10.1136/bmjqs-2017-007071 . Epub 2017 Nov 3. PMID: 29101291 Di Cristofaro L, Ruffolo C, Pinto E, Massa M, Antoniutti M, Cagol M, Massani M, Alfieri R, Costa A, Bassi N, Castoro C, Scarpa M (2014) Complications after surgery for colorectal cancer affect quality of life and surgeon-patient relationship. Colorectal Dis. ;16(12):O407-19. 10.1111/codi.12752 . PMID: 25155523 Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7133158","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":501107904,"identity":"278ebb69-c41b-4be8-858c-e384027f572e","order_by":0,"name":"Christina Schott","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAs0lEQVRIiWNgGAWjYJACA8l/NhAWD7FaCizY0kjU8qGC7TAJWvjbjz/ccIPnvN2GGwmMD962EaFF4kyOseEMidvJQC3MhnOJ0WLAkMNmLGFwO9nsRgKbNC9RWvifP//9J+EcSAv7b+K0SCQYGEgcOGAHsoWZKC0SN94YGEg2JCfYn3nYLDnnHBFa+PvTHwC12NlLticf/PCmjAgtMJDYwMDYQIJ6ILAnTfkoGAWjYBSMKAAA0Xg3UutorFYAAAAASUVORK5CYII=","orcid":"","institution":"Rosalind Franklin University of Medicine and Science","correspondingAuthor":true,"prefix":"","firstName":"Christina","middleName":"","lastName":"Schott","suffix":""},{"id":501107905,"identity":"543ae88e-5935-49fe-a886-ea71ec9026d8","order_by":1,"name":"Arthur Drouaud","email":"","orcid":"","institution":"George Washington University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Arthur","middleName":"","lastName":"Drouaud","suffix":""},{"id":501107906,"identity":"140bff51-e881-405c-99a2-93af0bf14ffa","order_by":2,"name":"Brandon Boyarsky","email":"","orcid":"","institution":"George Washington University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Brandon","middleName":"","lastName":"Boyarsky","suffix":""},{"id":501107907,"identity":"a572307d-58bd-43f1-be89-4500fd896cc5","order_by":3,"name":"Rachel Silverman","email":"","orcid":"","institution":"George Washington University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Rachel","middleName":"","lastName":"Silverman","suffix":""},{"id":501107908,"identity":"410d5a81-0fb8-4b82-ae03-92bcca23c4f5","order_by":4,"name":"Morgan Perry","email":"","orcid":"","institution":"Rosalind Franklin University of Medicine and Science","correspondingAuthor":false,"prefix":"","firstName":"Morgan","middleName":"","lastName":"Perry","suffix":""},{"id":501107909,"identity":"28ecb3f9-ce71-43ab-aeae-dc38639b4468","order_by":5,"name":"Marian Khalili","email":"","orcid":"","institution":"George Washington University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Marian","middleName":"","lastName":"Khalili","suffix":""},{"id":501107910,"identity":"e112da41-5261-47ba-af6b-c9b42a82b535","order_by":6,"name":"Matthew Ng","email":"","orcid":"","institution":"George Washington University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Matthew","middleName":"","lastName":"Ng","suffix":""}],"badges":[],"createdAt":"2025-07-15 17:53:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7133158/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7133158/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105035191,"identity":"89b9041f-adfa-4c53-b5af-49ff7658816b","added_by":"auto","created_at":"2026-03-20 07:25:39","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":681642,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7133158/v1/f391e7ee-ae46-42f7-a76b-d4aede385374.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"How to be a Better Colorectal Surgeon? A Sentimental Analysis of Patient Perceptions.","fulltext":[{"header":"INTRODUCTION","content":"\u003cp\u003ePhysician rating websites have a great impact on how patients\u0026rsquo; choose their doctors. We are able to gain a better understanding of patients\u0026rsquo; desires and concerns about their care by analyzing the reviews of former patients. Therefore, physicians and patients alike can gain meaningful insight on physician rating websites like \u003cspan type=\"Underline\" class=\"Underline\" name=\"Emphasis\"\u003ehealthgrades.com\u003c/span\u003e about the care that is provided by certain physicians and the attributes of physicians that patients are looking for [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Through the utilization of artificial intelligence and machine learning, we are able to perform sentiment analysis on large qualitative datasets and analyze text like patient reviews for positive and negative language. Machine learning sentiment analysis allows for a bulk review of patient feedback on physician attitudes, practice cleanliness and efficiency, and medical services provided [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e].\u003c/p\u003e\u003cp\u003ePreviously, sentiment analysis has been conducted on patients of several medical specialties, including psychiatrists, otolaryngologists, and vascular and orthopedic surgeons [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan additionalcitationids=\"CR7 CR8 CR9\" citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. These studies found that positive physician reviews include words like \u0026ldquo;kind,\u0026rdquo; \u0026ldquo;confident,\u0026rdquo; \u0026ldquo;recommend,\u0026rdquo; and \u0026ldquo;comfortable\u0026rdquo; that describe physician attributes, whereas negative physician reviews included both treatment and physician-specific words like \u0026ldquo;pain,\u0026rdquo; \u0026ldquo;side effects,\u0026rdquo; and \u0026ldquo;rude\u0026rdquo; [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan additionalcitationids=\"CR7 CR8 CR9\" citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. This sentiment analysis is the first to be conducted on qualitative reviews of CRS, who must balance treating an expanding patient population with a large number of complex and sensitive disease processes. A previous study conducted by Hill et al assessed quantitative metrics of CRS with numerical ratings [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. Disease-specific sentiment analyses pertinent to gastroenterology and colorectal surgery sought to understand patient perspectives on colorectal cancer and Lynch syndrome, respectively [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. We seek to conduct a sentiment analysis of the online reviews on healthgrades.com of CRS. The star ratings on healthgrades.com are based on patient reviews and reflect various aspects of a healthcare provider's service. Patients rate physicians on a scale of 1 to 5 stars, with 1 star indicating poor performance and 5 stars indicating excellent performance. Given that higher patient satisfaction is associated with better surgical outcomes, such as complications, mortality and readmission rates, it is essential to understand patients\u0026rsquo; opinions on physician behavior and the care they receive [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. However, complications in colorectal surgery, particularly those requiring additional surgeries, have been shown to have a significant negative impact on patient perception of the surgeon and the care they received [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]. Therefore, this analysis is particularly useful for CRS.\u003c/p\u003e"},{"header":"MATERIALS \u0026 METHODS","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003eColon and Rectal Surgeon data extraction\u003c/h2\u003e\u003cp\u003ePhysicians were identified using the directory from American Society of Colon and Rectal Surgeons (ASCRS). Since \u003cspan type=\"Underline\" class=\"Underline\" name=\"Emphasis\"\u003ehealthgrades.com\u003c/span\u003e only includes reviews of physicians from the United States, we limited our inclusion criteria to only surgeons practicing in the US. We excluded surgeons without written reviews on \u003cspan type=\"Underline\" class=\"Underline\" name=\"Emphasis\"\u003ehealthgrades.com\u003c/span\u003e. The surgeon names were inputted into a web-scraping code that searched Google for \u0026ldquo;(Physician Name) General Surgeon healthgrades.\u0026rdquo; To ensure we included all colorectal surgeons in our search, we chose to look up general surgeons instead of colorectal surgeons because ASCRS listed rural surgeons under general surgery on healthgrades.com. This resulted in a compilation of healthgrades surgeon profiles included in this study, which were used to pull written and star-rating reviews and demographic information. States included in each region for locational analysis followed the United States Census Bureau regions. Healthgrades was selected as it was consistently in the first five websites offered when searching Google for a provider and one of the only websites that permitted bulk data extraction.\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eSentiment analysis calculation\u003c/h3\u003e\n\u003cp\u003eSentiment analysis was conducted using \u0026ldquo;Valence Aware Dictionary and Sentiment Reasoner\u0026rdquo; (VADER) Python package. VADER is a widely used tool for analyzing and classifying the sentiment of text as positive, negative, or neutral. This classification is made by referencing a dictionary developed by 20 trained human raters, who assigned scores ranging from \u0026minus;\u0026thinsp;4 (most negative) to +\u0026thinsp;4 (most positive) to hundreds of words, with 0 representing neutral sentiment.\u003c/p\u003e\u003cp\u003eVADER obtained gold standard (human-validated) ground truth regarding sentiment intensity on corpora. For this purpose, 20 independent human raters from AMT were recruited. Quality control processes were implemented to help ensure meaningful data from the AMT raters. First, every rater was prescreened for English language reading comprehension. Second, every prescreened rater then had to complete an online sentiment rating training and orientation session, and score 90% or higher for matching the known (pre-validated) mean sentiment rating of lexical items. The training helped to ensure consistency in the rating rubric used by each independent rater. Third, every batch of 25 features contained five \u0026ldquo;golden items\u0026rdquo; with a known (pre-validated) sentiment rating distribution. If a worker was more than one standard deviation away from the mean of this known distribution on three or more of the five golden items, we discarded all 25 ratings in the batch from this worker. Finally, we implemented a bonus program to incentivize and reward the highest quality work. For example, we asked workers to select the valence score that they thought \u0026ldquo;most other people\u0026rdquo; would choose for the given lexical feature.\u003c/p\u003e\u003cp\u003eThis package parses sentences to sum and normalize the associated scores between \u0026minus;\u0026thinsp;1 (most negative) and +\u0026thinsp;1 (most positive). It recognizes punctuation, redundant capitalization, and adverbs, adjusting scores based on context. For example, \u0026ldquo;He was an AMAZING doctor\u0026rdquo; scores higher than \u0026ldquo;He was an amazing doctor,\u0026rdquo; and phrases like \u0026ldquo;very good\u0026rdquo; receive higher scores than \u0026ldquo;good,\u0026rdquo; while negations such as \u0026ldquo;not great\u0026rdquo; are scored negatively. Thus, VADER can provide a nuanced sentiment score for text based on the context and intensity of the words used.\u003c/p\u003e\n\u003ch3\u003eModel Validation and Data Analysis\u003c/h3\u003e\n\u003cp\u003eLinear regression analysis in Python was used to relate each surgeon\u0026rsquo;s average sentiment score to their average reported online star score, demonstrating the validity of the sentiment analysis. A significant correlation would indicate that the sentiment scores align with patient-reported star ratings. Student t-tests were performed to evaluate the relationship between sex and average sentiment score, while one-way ANOVA tests were used for age and geographic locations.\u003c/p\u003e\u003cp\u003e A word frequency analysis identified the most commonly used words in both the most positive and most negative reviews, excluding non-clinically relevant terms like \u0026ldquo;fabulous\u0026rdquo; or \u0026ldquo;best\u0026rdquo; to focus on practical insights. A bigram analysis provided context for frequently used words. Sentiment scores\u0026thinsp;\u0026gt;\u0026thinsp;+\u0026thinsp;0.50 were defined as positive reviews, and scores\u0026thinsp;\u0026lt;\u0026thinsp;0 as negative. Finally, a multiple logistic regression analyzed the impact of clinically relevant words or phrases on the likelihood of a review scoring\u0026thinsp;\u0026gt;\u0026thinsp;+\u0026thinsp;0.50.\u003c/p\u003e"},{"header":"RESULTS","content":"\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\u003ch2\u003eModel Validation\u003c/h2\u003e\u003cp\u003eWhen graphing the average score of each review with the calculated sentiment score, we observed a positive linear relationship (r\u0026sup2; = 0.439, p\u0026thinsp;\u0026lt;\u0026thinsp;0.01), which supports the validity of our analysis.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003eColorectal Surgeon Demographics\u003c/h2\u003e\u003cp\u003eOf the 4,065 surgeons initially identified, 3,292 U.S based surgeons were included in the final analysis. Healthgrades profiles were for 3,057 surgeons (2,139 males, 918 females). Of those, 1,819 had online reviews and 1,378 had written comments. The age distribution of surgeons was: under 40 (69), 40\u0026ndash;49 (443), 50\u0026ndash;59 (435), and over 60 (419). Increasing age was associated with decreasing mean sentiment score\u0026thinsp;+\u0026thinsp;0.567\u0026thinsp;\u0026plusmn;\u0026thinsp;0.299 for surgeons under 40, +\u0026thinsp;0.538\u0026thinsp;\u0026plusmn;\u0026thinsp;0.343 for ages 40\u0026ndash;49, +\u0026thinsp;0.498\u0026thinsp;\u0026plusmn;\u0026thinsp;0.341 for ages 50\u0026ndash;59, and +\u0026thinsp;0.471\u0026thinsp;\u0026plusmn;\u0026thinsp;0.365 for those over 60 (p\u0026thinsp;\u0026lt;\u0026thinsp;0.05) and mean star rating 4.466\u0026thinsp;\u0026plusmn;\u0026thinsp;0.640 for surgeons under 40, 4.313\u0026thinsp;\u0026plusmn;\u0026thinsp;0.612 for ages 40\u0026ndash;49, 4.206\u0026thinsp;\u0026plusmn;\u0026thinsp;0.610 for ages 50\u0026ndash;59, and 4.102\u0026thinsp;\u0026plusmn;\u0026thinsp;0.638 for those over 60 (p\u0026thinsp;\u0026lt;\u0026thinsp;0.05) (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). After analyzing a relationship between mean sentiment score and sex and mean star rating and sex, we found that men and women did not have a significant difference in either metric (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eSentiment Scores and Mean Star Scores of Colon and Rectal Surgeons based on Age.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"6\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;40\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003e40\u0026ndash;49\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003e50\u0026ndash;59\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026gt;\u0026thinsp;60\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eP-value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFrequency (N)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e69\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e443\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e435\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e419\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMean Sentiment Score Analysis\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e+\u0026thinsp;0.567\u0026thinsp;\u0026plusmn;\u0026thinsp;0.299\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e+\u0026thinsp;0.538\u0026thinsp;\u0026plusmn;\u0026thinsp;0.343\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e+\u0026thinsp;0.498\u0026thinsp;\u0026plusmn;\u0026thinsp;0.341\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e+\u0026thinsp;0.471\u0026thinsp;\u0026plusmn;\u0026thinsp;0.365\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.0149\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMean Star Score Analysis\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e4.466\u0026thinsp;\u0026plusmn;\u0026thinsp;0.640\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e4.313\u0026thinsp;\u0026plusmn;\u0026thinsp;0.612\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e4.206\u0026thinsp;\u0026plusmn;\u0026thinsp;0.610\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e4.102\u0026thinsp;\u0026plusmn;\u0026thinsp;0.638\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"6\"\u003e*Statistically significant\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eSentiment Scores and Mean Star Scores of Colon and Rectal Surgeons based on Sex.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSex\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMale\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eFemale\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003ep-value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFrequency\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1034\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e344\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMean Sentiment Score Analysis\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e+\u0026thinsp;0.507\u0026thinsp;\u0026plusmn;\u0026thinsp;0.343\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e+\u0026thinsp;0.506\u0026thinsp;\u0026plusmn;\u0026thinsp;0.360\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.95\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMean Star Score Analysis\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e4.256\u0026thinsp;\u0026plusmn;\u0026thinsp;0.778\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e4.198\u0026thinsp;\u0026plusmn;\u0026thinsp;0.878\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.06\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eWord/Word Pair Reviews\u003c/h3\u003e\n\u003cp\u003e A subset of the 6986 reviews analyzed were categorized into positive or negative reviews based on the sentiment scores. Words such as \"care,\" \"caring,\" \"kind,\" \"wonderful,\" and \"compassionate\" were more commonly used in positive reviews with frequencies of 718, 434, 350, 288, and 240, respectively. However, words such as \"no,\" \"pain,\" \"cancer,\" \"care,\" and \"problem\" were more commonly used in negative reviews with frequencies of 463, 403, 230, 188, and 159, respectively.\u003c/p\u003e\u003cp\u003eThe most frequent word pairs in positive reviews were \"(kind, caring)\" (102), \"(saved, life)\" (93), \"(feel, comfortable)\" (90), \"(kind, compassionate)\" (66), and \"(truly, cares)\" (62). Conversely, the most common word pairs in negative reviews were \"(colon, cancer)\" (55), \"(no, pain)\" (54), \"(cancer, free)\" (34), \"(saved, life)\" (34), and \"(no, one)\" (33).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eCommon Words and their Frequencies in Positive and Negative Reviews\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePositive Reviews Words\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eFrequency (N)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eNegative Reviews Word\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eFrequency (N)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ecare\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e718\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eno\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e463\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ecaring\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e434\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003epain\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e403\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ekind\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e350\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003ecancer\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e230\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ewonderful\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e288\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003ecare\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e188\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ecompassionate\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e240\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eproblem\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e159\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ecomfortable\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e198\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003erude\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e137\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003efriendly\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e185\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003ehorrible\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e83\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003etruly\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e184\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003ehelp\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e79\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003egrateful\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e174\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eworst\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e77\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ebetter\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e166\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003ewant\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e72\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eCommon Word-Pairs and Their Frequencies in Positive and Negative Reviews\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePositive Reviews Word-Pair\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eFrequency (N)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eNegative Reviews Word-Pairs\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eFrequency (N)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(kind, caring)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e102\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(colon, cancer)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e55\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(saved, life)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e93\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(no, pain)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e54\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(feel, comfortable)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e90\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(cancer, free)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(kind, compassionate)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e66\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(saved, life)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(truly, cares)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e62\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(no, one)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e33\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(god, bless)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(severe, pain)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e28\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(caring, compassionate)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e56\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(excruciating, pain)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e26\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(make, sure)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(waste, time)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e23\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(took, care)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e52\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(no, problems)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e22\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(cares, patients)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(emergency, surgery)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e21\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\n\u003ch3\u003eMultivariate Analysis\u003c/h3\u003e\n\u003cp\u003eMultivariate analysis identified words that significantly impact the likelihood that a physician receives a positive or negative review. For example, the word \u0026ldquo;approachable\u0026rdquo; increased the likelihood of a physician receiving a positive review (odds ratio (OR): 2.23, p\u0026thinsp;\u0026lt;\u0026thinsp;0.05), however, the word \u0026ldquo;rude\u0026rdquo; decreased the odds of receiving a positive review (OR: 0.09; p\u0026thinsp;\u0026lt;\u0026thinsp;0.05).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eMultivariant analysis of relevant keywords with a positive influence on reviews.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"3\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePositive Words\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eOR (97.5% CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eP-value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003econfident\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e6.49 (3.84\u0026ndash;10.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eaccessible\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e6.29 (1.39\u0026ndash;28.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ekind\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.80 (2.84\u0026ndash;5.08)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003erelief\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.58 (1.32\u0026ndash;9.75)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003epain-free\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.51 (1.27\u0026ndash;9.72)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003erecommend\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.05 (2.67\u0026ndash;3.48)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eempathetic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.01 (0.93\u0026ndash;9.66)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.06\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ewarm\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.80 (1.44\u0026ndash;5.42)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003elistens\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.79 (1.91\u0026ndash;4.06)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ecomfortable\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.51 (1.96\u0026ndash;3.22)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eexplains\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.47 (1.80\u0026ndash;3.38)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003estaff\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.31 (1.99\u0026ndash;2.68)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eapproachable\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.23 (0.54\u0026ndash;9.19)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.27\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ebedside-manner\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.97 (1.46\u0026ndash;2.66)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eparking\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.94 (0.31\u0026ndash;12.27)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.48\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eknowledgeable\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.46 (1.12\u0026ndash;1.90)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ecourtesy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.41 (0.17\u0026ndash;11.78)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.75\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eadvocate\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.39 (0.35\u0026ndash;5.49)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.64\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003erefer\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.37 (0.74\u0026ndash;2.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.32\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003enurse\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.18 (0.84\u0026ndash;1.66)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.34\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003emedication\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.07 (0.47\u0026ndash;2.45)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.88\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"3\"\u003e*Statistically significant\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab6\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eMultivariant analysis of relevant keywords with negative influence on reviews.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"3\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNegative Words\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eOR (97.5% CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eP-Value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003erude\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.094 (0.041\u0026ndash;0.215)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003earrogant\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.117 (0.035\u0026ndash;0.395)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eold\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.520 (0.424\u0026ndash;0.637)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.05*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003erushed\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.689 (0.429\u0026ndash;1.108)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.12\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003esevere-pain\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.766 (0.191\u0026ndash;3.063)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.71\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ewalking\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.780 (0.348\u0026ndash;1.747)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.55\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eemergency\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.837 (0.599\u0026ndash;1.170)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.30\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eyoung\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.838 (0.393\u0026ndash;1.787)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.65\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eorganized\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.887 (0.368\u0026ndash;2.138)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.79\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"3\"\u003e*Statistically significant\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e"},{"header":"DISCUSSION","content":"\u003cp\u003eIncreased patient education and ease of access to medical information on the internet are likely contributing to the rapid growth in patient volume experienced by CRS. Reports have shown that 72% of surgeons have a practice website and 43% of patients have searched for their doctors online [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. Additionally, the proportion of cases treated by high-volume CRS has also increased, pointing to a potential link between patient education and surgeon selection [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eUnderstanding how physicians are rated and reviewed online is essential to providing the highest quality of care and attracting future patients. The goal of this study is to analyze the language used to describe CRS with high and low patient ratings and identify characteristics associated with those ratings. Our research, which included 1,378 surgeons, is the second-largest cohort to date studied using physician review websites. Additionally, it includes the highest number of written reviews and is the only study to utilize written sentiment for this purpose. We discovered physicians described as caring, kind, compassionate, and comfortable and provide sufficient pain management received the highest ratings on online reviews.\u003c/p\u003e\u003cp\u003eOur research shows that there are several key factors that influence patient ratings of CRS. According to a \u003cspan type=\"Underline\" class=\"Underline\" name=\"Emphasis\"\u003ehealthgrades.com\u003c/span\u003e report on the predictors of high ratings in CRS, younger surgeons with 1\u0026ndash;9 years of experience were 2.76 times more likely to receive high ratings, indicating that patients have a more positive perception of younger surgeon [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. Similarly, our analysis showed that younger CRS have significantly more positive written reviews (\u0026lt;\u0026thinsp;40: +0.567, 40\u0026ndash;49: +.538, 50\u0026ndash;59: +.498, \u0026gt;\u0026thinsp;59: +0.471; \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;.014) and star ratings (\u0026lt;\u0026thinsp;40: 4.466, 40\u0026ndash;49: 4.313, 50\u0026ndash;59: 4.206, \u0026gt;\u0026thinsp;59: 4.102; \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01) than older surgeons. In light of these findings, we recommend that middle-aged surgeons incorporate these positive characteristics which are described later in this study. These findings are consistent with previous observations that younger surgeons prefer minimally invasive surgical techniques [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. Additionally, residencies today emphasize interpersonal skills and communication throughout their selection process which may contribute to more positive patient ratings. Another study analyzed reviews of general surgeons from RateMDs.com and Yelp.com, and found there was no significant gender difference in overall ratings (83.7% positive for men vs. 74.3% for women, P\u0026thinsp;=\u0026thinsp;0.08) [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. Our findings align with this study as we found men had a sentiment score of +\u0026thinsp;0.507 and women\u0026thinsp;+\u0026thinsp;0.506 (P\u0026thinsp;=\u0026thinsp;0.955), with star ratings of 4.256 for men and 4.198 for women (P\u0026thinsp;=\u0026thinsp;0.0648).\u003c/p\u003e\u003cp\u003e Our study found that physician characteristics and interpersonal relationships were more likely to be associated with positive reviews, while words about the patient\u0026rsquo;s disease were more likely to be associated with negative reviews. These findings are in line with sentiment analysis of patient reviews in other surgical fields [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan additionalcitationids=\"CR7 CR8\" citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. We explored the specific language and drivers behind these findings.\u003c/p\u003e\u003cp\u003eInterpersonal characteristics such as active listening and empathetic responses, along with clinical knowledge, have been shown to enhance physician-patient relationships [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. Our study found that surgeons were significantly more likely to get positive reviews when they appeared confident (OR: 6.49), accessible (OR: 6.29), listened attentively (OR: 2.79), and were kind (OR: 3.80). Additionally, words such as \"care\" and \"kind\" were more frequently used in positive reviews. The four most common words and word pairs in these reviews were associated with interpersonal characteristics. Shared decision making is made possible by quality communication between the patient and provider [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. Patients perceive openness, agreeableness, and emotional stability as favorable traits in CRS. Despite acknowledging that a surgeon\u0026rsquo;s personality may not affect post-operative complication rates, patients believe it would significantly change complication management. This underscores the importance of promoting positive interpersonal characteristics for both patient satisfaction and effective complication management [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. Therefore it is essential to continue promoting positive interpersonal characteristics through education, such as patient simulations and constructive feedback.\u003c/p\u003e\u003cp\u003eOn the other hand, physicians who were perceived as rude (OR: 0.09), arrogant (OR: 0.12), and old (OR: 0.52) were significantly more likely to receive negative reviews. This is consistent with our finding that older surgeons received worse reviews. Moreover, disease and pain-related words were more frequently used in negative reviews. In the field of colon and rectal surgery, 39% of rectal cancer patients reported unclear communication with their physicians, particularly among younger patients and those in larger hospitals, which led to consistently lower scores in role, emotional, and social functioning [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eThe words \u0026ldquo;cancer\u0026rdquo; and \u0026ldquo;colon-cancer\u0026rdquo; were among the most frequently used words in negative reviews. Patient disease is a factor outside of physicians control that may negatively impact patient perception and most physicians report having difficulty during these conversations. For example, in the United States, colorectal cancer ranks as the second leading cause of cancer-related deaths; this fact negatively influences patients\u0026rsquo; perceptions of providers when they receive a colorectal cancer diagnosis [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]. Poor doctor-patient communication skills can be linked with adverse outcomes for patients such as higher rates of anxiety and depression, and worse psychological adaptation to their new diagnosis [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. Therefore, there is need for improvement in this area of the colorectal cancer community.\u003c/p\u003e\u003cp\u003eWhen delivering \u0026lsquo;bad\u0026rsquo; news, physicians should speak in an unhurried, honest, balanced, and empathic fashion to produce greater satisfaction with the encounter. Important aspects of these conversations entail understanding the patient's expectations, giving a forewarning of bad news, discussing this new diagnosis at the patient's preferred pace, giving adequate time for the patient to react, and addressing their questions and concerns. Strategies for improving physician-patient communication include communication training courses for medical students and physicians along with supplying summaries of difficult discussions to improve recollection and satisfaction with communication for patients [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. Our findings stress the importance of improved communication techniques for both current and future CRS.\u003c/p\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003eLimitations\u003c/h2\u003e\u003cp\u003eWe acknowledge several limitations in this study. Firstly, \u003cspan type=\"Underline\" class=\"Underline\" name=\"Emphasis\"\u003ehealthgrades.com\u003c/span\u003e was our only source of patient reviews because it was the only place from which we could freely extract data, potentially introducing bias. The reviews on healthgrades.com are not subject to a verification process which allows anyone to write a review about any healthcare provider, potentially impacting the reliability of the information. Additionally, the subjective nature of ratings and reviews on public websites prevented us from understanding the specific reasons behind patients' comments. We couldn't differentiate between remarks about the physician and non-physician factors in our overall sentiment analysis scores. Some other factors that were not readily available to us through healthgrades.com and may be beneficial to review in the future include demographic factors of physicians and their practices such as race, type of practice (academic vs. community), setting of practice; and patient demographics such as race, sexual orientation, and socioeconomic status. Furthermore, by using the \"American Society of Colon and Rectal Surgeons\" directory to compile our surgeon list, our analysis was limited to a portion of all CRS. Further developments for this study include the creation of an app or website that would give providers a place to input their websites and reviews to receive individualized performance feedback. A machine learning-based app would enable surgeons to receive feedback in real time and adjust their practices as needed.\u003c/p\u003e\u003c/div\u003e"},{"header":"CONCLUSION","content":"\u003cp\u003eOur study utilized machine-learning sentiment analysis of online patient reviews to determine positive and negative attributes of CRS. By implementing VADER analysis on \u003cspan type=\"Underline\" class=\"Underline\" name=\"Emphasis\"\u003ehealthgrades.com\u003c/span\u003e patient reviews, we revealed that younger CRS were more likely to have positive patient reviews and more positive interpersonal characteristics such as empathy and confidence. Poor communication skills, negative personality traits, and rushed encounters were associated with lower patient ratings of CRS. Disease-specific words like \u0026ldquo;cancer\u0026rdquo; and \u0026ldquo;pain\u0026rdquo; significantly contributed to negative patient opinions. To increase patient satisfaction, we recommend all CRS apply favorable interpersonal skills which are emphasized in more recent medical training.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eFunding/Support\u003c/strong\u003e:\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eNo Source of Fundings.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFinancial Disclosures\u003c/strong\u003e:\u003c/p\u003e\n\u003cp\u003eNo Financial Disclosures\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting Interests:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll authors have no competing interests to declare\u003c/p\u003e\n\u003ch2\u003e\u0026nbsp;\u003c/h2\u003e\n\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\n\u003cp\u003eC.S., A.D., B.B., R.S., and M.P. wrote the main manuscript. A.D. prepared all figures and tables. All authors reviewed the manuscript.\u003c/p\u003e\n\u003ch2\u003eData Availability\u003c/h2\u003e\n\u003cp\u003eThe data collected are available through healthgrades.com using physician names found through https://imis.fascrs.org/portal/portal/Member_Directory/Find-a-Colorectal-Surgeon.aspx?_gl=1*1st49zz*_ga*MTIxNTE0OTc4Ni4xNzUyNzc0MDAx*_ga_M0BRWHHY9M*czE3NTI3NzQwMDEkbzEkZzAkdDE3NTI3NzQwMDEkajYwJGwwJGgw\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eLeibovich BC (2018) Correlation of Online Physician Reviews and Overall Patient Satisfaction. \u003cem\u003eMayo Clin Proc\u003c/em\u003e. ;93(4):404\u0026ndash;405. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.mayocp.2018.02.021\u003c/span\u003e\u003cspan address=\"10.1016/j.mayocp.2018.02.021\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePark SH, Cheng CP, Buehler NJ, Sanford T, Torrey W (2023) A sentiment analysis on online psychiatrist reviews to identify clinical attributes of psychiatrists that shape the therapeutic alliance. Front Psychiatry 14:1174154. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fpsyt.2023.1174154\u003c/span\u003e\u003cspan address=\"10.3389/fpsyt.2023.1174154\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eIglesias CA, Moreno A (eds) (2020) Sentiment Analysis for Social Media. MDPI - Multidisciplinary Digital Publishing Institute. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/books978-3-03928-573-0\u003c/span\u003e\u003cspan address=\"10.3390/books978-3-03928-573-0\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGreaves F, Ramirez-Cano D, Millett C, Darzi A, Donaldson L (2013) Use of sentiment analysis for capturing patient experience from free-text comments posted online. J Med Internet Res 15(11):e239. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.2196/jmir.2721\u003c/span\u003e\u003cspan address=\"10.2196/jmir.2721\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePandey AR, Seify M, Okonta U, Hosseinian-Far A (2023) Advanced Sentiment Analysis for Managing and Improving Patient Experience: Application for General Practitioner (GP) Classification in Northamptonshire. Int J Environ Res Public Health 20(12):6119. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/ijerph20126119\u003c/span\u003e\u003cspan address=\"10.3390/ijerph20126119\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eVasan V, Cheng CP, Lerner DK, Vujovic D, van Gerwen M, Iloreta AM (2023) A natural language processing approach to uncover patterns among online ratings of otolaryngologists. J Laryngol Otol 137(12):1384\u0026ndash;1388. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1017/S0022215123000476\u003c/span\u003e\u003cspan address=\"10.1017/S0022215123000476\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTang J, Arvind V, White CA, Dominy C, Cho S, Kim JS (2023) How are Patients Describing You Online? A Natural Language Processing Driven Sentiment Analysis of Online Reviews on CSRS Surgeons. Clin Spine Surg 36(2):E107\u0026ndash;E113. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1097/BSD.0000000000001372\u003c/span\u003e\u003cspan address=\"10.1097/BSD.0000000000001372\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCho LD, Tang JE, Pitaro N et al (2023) Sentiment Analysis of Online Patient-Written Reviews of Vascular Surgeons. Ann Vasc Surg 88:249\u0026ndash;255. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.avsg.2022.07.016\u003c/span\u003e\u003cspan address=\"10.1016/j.avsg.2022.07.016\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTang JE, Arvind V, White CA et al (2023) Using Sentiment Analysis to Understand What Patients Are Saying About Hand Surgeons Online. Hand (N Y) 18(5):854\u0026ndash;860. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/15589447211060439\u003c/span\u003e\u003cspan address=\"10.1177/15589447211060439\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCasciato DJ, Mateen S AI-Assisted Sentiment Analysis of ACFAS Fellowship-Trained Foot and Ankle Surgeon Online Reviews. \u003cem\u003eJ Foot Ankle Surg\u003c/em\u003e. Published online June 13, 2024:S1067-2516(24)00113-3. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1053/j.jfas.2024.05.014\u003c/span\u003e\u003cspan address=\"10.1053/j.jfas.2024.05.014\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHill SS, Hoang CM, Cheraghi SN et al (2020) Data Accuracy and Predictors of High Ratings of Colon and Rectal Surgeons on an Online Physician Rating Website. Dis Colon Rectum 63(2):226\u0026ndash;232. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1097/DCR.0000000000001539\u003c/span\u003e\u003cspan address=\"10.1097/DCR.0000000000001539\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePortier K, Greer GE, Rokach L et al (2013) Understanding topics and sentiment in an online cancer survivor community. J Natl Cancer Inst Monogr 2013(47):195\u0026ndash;198. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1093/jncimonographs/lgt025\u003c/span\u003e\u003cspan address=\"10.1093/jncimonographs/lgt025\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBian J, Zhao Y, Salloum RG et al (2017) Using Social Media Data to Understand the Impact of Promotional Information on Laypeople\u0026rsquo;s Discussions: A Case Study of Lynch Syndrome. J Med Internet Res 19(12):e414. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.2196/jmir.9266\u003c/span\u003e\u003cspan address=\"10.2196/jmir.9266\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHutto C, Gilbert E (2014) VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text. \u003cem\u003eProceedings of the International AAAI Conference on Web and Social Media\u003c/em\u003e. ;8(1):216\u0026ndash;225. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1609/icwsm.v8i1.14550\u003c/span\u003e\u003cspan address=\"10.1609/icwsm.v8i1.14550\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLong LE, Leung C, Hong JS, Wright C, Young CJ (2019) Patterns of internet and social media use in colorectal surgery. BMC Surg 19(1):52. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12893-019-0518-4\u003c/span\u003e\u003cspan address=\"10.1186/s12893-019-0518-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJolly K, Parry J, Rouse A, Stevens A (2001) Volumes of cancer surgery for breast, colorectal and ovarian cancer 1992-97: Is there evidence of increasing sub-specialization by surgeons? Br J Cancer 84(10):1308\u0026ndash;1313. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1054/bjoc.2001.1794\u003c/span\u003e\u003cspan address=\"10.1054/bjoc.2001.1794\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDulskas A, Caushaj PF, Grigoravicius D et al (2023) International Society of University Colon and Rectal Surgeons survey of surgeons\u0026rsquo; preference on rectal cancer treatment. Ann Coloproctol 39(4):307\u0026ndash;314. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3393/ac.2022.00255.0036\u003c/span\u003e\u003cspan address=\"10.3393/ac.2022.00255.0036\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLam CC, Zimmern A (2021) Colon and Rectal Surgery Residency Selection Criteria: A National Program Director Survey. J Surg Educ 78(2):519\u0026ndash;524. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jsurg.2020.07.030\u003c/span\u003e\u003cspan address=\"10.1016/j.jsurg.2020.07.030\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMarrero K, King E, Fingeret AL (2020) Impact of Surgeon Gender on Online Physician Reviews. J Surg Res 245:510\u0026ndash;515. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jss.2019.07.047\u003c/span\u003e\u003cspan address=\"10.1016/j.jss.2019.07.047\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTallman K, Janisse T, Frankel RM, Sung SH, Krupat E, Hsu JT (2007) Communication Practices of Physicians With High Patient-Satisfaction Ratings. \u003cem\u003ePerm J\u003c/em\u003e. ;11(1):19\u0026ndash;29. Accessed August 14, 2024. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC3061374/\u003c/span\u003e\u003cspan address=\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3061374/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAustin CA, Mohottige D, Sudore RL, Smith AK, Hanson LC (2015) Tools to Promote Shared Decision Making in Serious Illness: A Systematic Review. JAMA Intern Med 175(7):1213\u0026ndash;1221. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1001/jamainternmed.2015.1679\u003c/span\u003e\u003cspan address=\"10.1001/jamainternmed.2015.1679\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBisset CN, Dames N, Oliphant R et al (2020) Exploring shared surgical decision-making from the patient\u0026rsquo;s perspective: is the personality of the surgeon important? Colorectal Dis 22(12):2214\u0026ndash;2221. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/codi.15237\u003c/span\u003e\u003cspan address=\"10.1111/codi.15237\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKerr J, Jutta Engel MD, Anne Schlesinger Raab MPH, Hansjorg Sauer MD, Holzel D (2003) PhD. Doctor-Patient Communication. Dis Colon Rectum 46(8):1038\u0026ndash;1046. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s10350-004-7278-6\u003c/span\u003e\u003cspan address=\"10.1007/s10350-004-7278-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSiegel RL, Wagle NS, Cercek A, Smith RA, Jemal A (2023) Colorectal cancer statistics, 2023. Cancer J Clin 73(3):233\u0026ndash;254. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3322/caac.21772\u003c/span\u003e\u003cspan address=\"10.3322/caac.21772\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eEllis PM, Tattersall MH (1999) How should doctors communicate the diagnosis of cancer to patients? Ann Med 31(5):336\u0026ndash;341. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3109/07853899908995900\u003c/span\u003e\u003cspan address=\"10.3109/07853899908995900\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLobo Prabhu K, Cleghorn MC, Elnahas A, Tse A, Maeda A, Quereshy FA, Okrainec A, Jackson TD (2018) Is quality important to our patients? The relationship between surgical outcomes and patient satisfaction. BMJ Qual Saf. ;27(1):48\u0026ndash;52. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1136/bmjqs-2017-007071\u003c/span\u003e\u003cspan address=\"10.1136/bmjqs-2017-007071\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Epub 2017 Nov 3. PMID: 29101291\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDi Cristofaro L, Ruffolo C, Pinto E, Massa M, Antoniutti M, Cagol M, Massani M, Alfieri R, Costa A, Bassi N, Castoro C, Scarpa M (2014) Complications after surgery for colorectal cancer affect quality of life and surgeon-patient relationship. Colorectal Dis. ;16(12):O407-19. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/codi.12752\u003c/span\u003e\u003cspan address=\"10.1111/codi.12752\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. PMID: 25155523\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Colon and rectal surgeons, healthgrades, Patient satisfaction, Physician rating Web sites","lastPublishedDoi":"10.21203/rs.3.rs-7133158/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7133158/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003ePURPOSE\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eDue to the sensitive nature of colorectal surgery discussions and exams, patient opinions and attitudes towards their providers are an essential part of quality colorectaal surgery care. There are a multitude of factors related to both providers and patients that impact patients’ opinions. These include factors such as patient and provider demographics, personality traits, communication skills, and disease specific factors.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMETHODS\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study analyzed online reviews to better grasp the relationship between patient sentiment scores and demographics of colon and rectal surgeons (CRS). Analysis of patient reviews was performed using machine learning. Additionally, it looks at how key terms found in patient reviews of CRS relate to overall patient sentiment.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eRESULTS\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAnalysis included 6,986 patient reviews of 1,378 CRS. Younger surgeon age was associated with higher mean sentiment analysis scores and star ratings (P \u0026lt; .01). After word frequency analysis, our study found that patient reviews containing certain clinically relevant terms had an increased likelihood of receiving a positive review. Additionally, poor communication skills, negative personality traits, and rushed encounters were associated with lower surgeon ratings.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCONCLUSION\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003ePhysician attributes and disease specific factors both significantly impact patients’ opinions. Favorable interpersonal skills of CRS are essential to patient satisfaction. Additionally, our study found that disease specific terms like “pain” and “cancer” were associated with negative reviews indicating that patient satisfaction extends beyond traits inherent to CRS such as demographics and behavior.\u003c/p\u003e","manuscriptTitle":"How to be a Better Colorectal Surgeon? A Sentimental Analysis of Patient Perceptions.","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-21 08:44:56","doi":"10.21203/rs.3.rs-7133158/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"77039406-8984-44e4-9c72-abc667d8fd28","owner":[],"postedDate":"August 21st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-19T03:55:05+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-21 08:44:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7133158","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7133158","identity":"rs-7133158","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}